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. 106136
    Prev
    Next
    INDEX
    Explanations

    period

    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
    ালে
    -0.08
     vibrator
    -0.08
    iever
    -0.08
     busiest
    -0.07
     teoria
    -0.07
    ivial
    -0.07
    筆
    -0.07
     sw
    -0.07
    ানে
    -0.07
    IVAL
    -0.07
    POSITIVE LOGITS
    .capitalize
    0.08
    esar
    0.08
    .fact
    0.08
     بوك
    0.08
    agoza
    0.07
     Monsters
    0.07
     واف
    0.07
    лат
    0.07
    	sprintf
    0.07
    ,好
    0.07
    Activations Density 0.058%

    No Known Activations