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

    Neuronpedia

    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. 23-RESID-POST-AA
    11. 96554
    Prev
    Next
    INDEX
    Explanations

    воз

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ıştır
    -0.08
    ist
    -0.08
    iyay
    -0.07
    HIR
    -0.07
    estial
    -0.07
    'ét
    -0.07
    инчи
    -0.07
     först
    -0.07
    oj
    -0.07
    wach
    -0.07
    POSITIVE LOGITS
     friendliness
    0.08
     na
    0.08
    глав
    0.08
    на
    0.07
    na
    0.07
     nae
    0.07
    ым
    0.07
     métier
    0.07
     naï
    0.07
    uon
    0.07
    Activations Density 0.001%

    No Known Activations