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. 78371
    Prev
    Next
    INDEX
    Explanations

    more

    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
     betreff
    -0.09
     colectivos
    -0.09
     forty
    -0.08
    ДУ
    -0.08
     Couldn't
    -0.08
    /meta
    -0.08
     Something
    -0.08
     Dö
    -0.08
     belangrijke
    -0.08
     кое
    -0.08
    POSITIVE LOGITS
     pronounced
    0.09
     pleasant
    0.09
     Sop
    0.08
     aware
    0.08
     sed
    0.08
     subtle
    0.08
    适
    0.08
    容易
    0.08
     robust
    0.08
     suited
    0.08
    Activations Density 0.058%

    No Known Activations