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. 48487
    Prev
    Next
    INDEX
    Explanations

    configurations and code

    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
    orzyst
    -0.08
     ping
    -0.08
     confianza
    -0.08
    cope
    -0.08
     повтор
    -0.08
    çi
    -0.07
     affair
    -0.07
     Flores
    -0.07
     Grâce
    -0.07
    COPE
    -0.07
    POSITIVE LOGITS
     lame
    0.07
    =g
    0.07
     goth
    0.07
     cumple
    0.07
    玩家
    0.07
     probability
    0.07
     positively
    0.07
    roken
    0.07
     sre
    0.07
    rae
    0.07
    Activations Density 0.000%

    No Known Activations