© 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
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 618
    Prev
    Next
    INDEX
    Explanations

    partial derivatives

    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
     makeover
    -0.08
    -служ
    -0.08
     fitting
    -0.08
    -pand
    -0.08
    Strike
    -0.08
    Gap
    -0.08
    Outra
    -0.08
    Claro
    -0.08
    Os
    -0.07
    Vamos
    -0.07
    POSITIVE LOGITS
     Editable
    0.09
     Dependencies
    0.08
     supervising
    0.08
     cou
    0.08
     सहभागी
    0.08
     pyr
    0.08
     Parameter
    0.08
     competed
    0.07
     Ranking
    0.07
     Pools
    0.07
    Activations Density 0.012%

    No Known Activations