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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 78984
    Prev
    Next
    INDEX
    Explanations

    family relations and similarity

    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
    Anyone
    -0.09
     Jews
    -0.08
    Worth
    -0.08
     kto
    -0.08
    ifiers
    -0.08
    IFIER
    -0.08
    Iedere
    -0.07
    Jeg
    -0.07
     Küche
    -0.07
    Point
    -0.07
    POSITIVE LOGITS
     counterpart
    0.14
     counterparts
    0.12
     cousin
    0.11
     sister
    0.10
     brother
    0.09
     Schwester
    0.09
    哥哥
    0.09
     hermano
    0.09
    兄
    0.09
     hermana
    0.09
    Activations Density 0.039%

    No Known Activations