© 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 EvalsExportsAPI 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. 113653
    Prev
    Next
    INDEX
    Explanations

    pie charts, degrees

    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
    HOOK
    -0.09
     geren
    -0.09
     penetrating
    -0.08
    rauch
    -0.08
     настав
    -0.08
    Torch
    -0.08
    KIT
    -0.08
     проник
    -0.08
    TOR
    -0.08
    MOVE
    -0.08
    POSITIVE LOGITS
     percentages
    0.12
    Percentage
    0.12
     Percentage
    0.11
     percentage
    0.11
    _percentage
    0.11
     ശതമ
    0.10
     प्रतिशत
    0.10
    percentage
    0.10
     porcent
    0.10
     Percent
    0.10
    Activations Density 0.010%

    No Known Activations