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. 77401
    Prev
    Next
    INDEX
    Explanations

    face shapes

    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
     CDS
    -0.09
    secution
    -0.08
    KR
    -0.08
     teknologi
    -0.08
    see
    -0.08
     KR
    -0.08
     vital
    -0.08
     movimiento
    -0.08
     chapter
    -0.08
     bootstrap
    -0.07
    POSITIVE LOGITS
     việc
    0.09
    ubble
    0.09
     akkoord
    0.08
    _ROWS
    0.08
    glich
    0.08
    ائيل
    0.08
     liking
    0.08
     تقريب
    0.08
     يستطيع
    0.08
    性生活
    0.08
    Activations Density 0.001%

    No Known Activations