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. 111946
    Prev
    Next
    INDEX
    Explanations

    of

    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
     Abenteuer
    -0.09
     Verbesser
    -0.08
     Ö
    -0.08
     améliorer
    -0.08
     son
    -0.08
     avont
    -0.08
     amélior
    -0.08
     conspir
    -0.08
     jõ
    -0.08
     aventuras
    -0.08
    POSITIVE LOGITS
    ((((
    0.09
     prescribed
    0.08
     mercy
    0.08
    .exit
    0.08
    guided
    0.08
     segunda
    0.08
    edict
    0.08
    higher
    0.07
    (rem
    0.07
    ichever
    0.07
    Activations Density 0.001%

    No Known Activations