Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 43683
    Prev
    Next
    INDEX
    Explanations

    voice

    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
     normalization
    -0.09
     playback
    -0.08
     algebra
    -0.08
     verdieping
    -0.07
    _cancel
    -0.07
     amplitude
    -0.07
    981
    -0.07
    Normalizer
    -0.07
    _v
    -0.07
     worth
    -0.07
    POSITIVE LOGITS
     skle
    0.09
    ремя
    0.09
     thống
    0.08
     regret
    0.08
    0.08
     gritty
    0.08
    .DEF
    0.08
     glove
    0.08
     โม
    0.07
    ,引
    0.07
    Activations Density 0.004%

    No Known Activations