© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 70544
    Prev
    Next
    INDEX
    Explanations

    Probability/chance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anium
    -0.09
    Typography
    -0.08
    Axes
    -0.08
    nec
    -0.08
     typography
    -0.08
     axes
    -0.08
    андары
    -0.08
     vallée
    -0.08
    klan
    -0.07
    상의
    -0.07
    POSITIVE LOGITS
     probability
    0.20
     probabilities
    0.17
     Probability
    0.16
    _probability
    0.16
    概率
    0.16
    Probability
    0.15
     вероятность
    0.15
    _prob
    0.13
     احتمال
    0.13
     Wahrscheinlichkeit
    0.12
    Activations Density 0.030%

    No Known Activations