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. 65790
    Prev
    Next
    INDEX
    Explanations

    helium

    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
    �
    -0.08
    Walker
    -0.08
    咪
    -0.08
     거리
    -0.07
     simp
    -0.07
    િતા
    -0.07
    Bart
    -0.07
     ம
    -0.07
     enlist
    -0.07
     Cory
    -0.07
    POSITIVE LOGITS
     biom
    0.08
     Lydia
    0.08
     п
    0.07
    寄
    0.07
    /she
    0.07
    ালে
    0.07
    AO
    0.07
     hath
    0.07
     prescribing
    0.07
    তম
    0.07
    Activations Density 0.019%

    No Known Activations