Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11685
    Prev
    Next
    INDEX
    Explanations

    from

    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
     évol
    -0.08
     Municipio
    -0.08
     пед
    -0.08
     ambit
    -0.08
     reš
    -0.07
    wjgl
    -0.07
    �
    -0.07
     bon
    -0.07
    raised
    -0.07
    ари
    -0.07
    POSITIVE LOGITS
    :i
    0.07
     feature
    0.07
    .Toolkit
    0.07
    Hall
    0.07
    (feature
    0.07
    نين
    0.07
     aanr
    0.07
    *i
    0.07
     kontr
    0.07
    ,:,:
    0.07
    Activations Density 0.000%

    No Known Activations