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. 49270
    Prev
    Next
    INDEX
    Explanations

    General language and math

    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
     limitation
    -0.09
     drawback
    -0.08
     considerando
    -0.08
     justification
    -0.07
    隐藏
    -0.07
     naszym
    -0.07
     hidden
    -0.07
     concealed
    -0.07
     possession
    -0.07
     motivos
    -0.07
    POSITIVE LOGITS
     رای
    0.09
    ूद
    0.08
    vano
    0.08
     дел
    0.08
     ihr
    0.08
    ther
    0.08
    db
    0.08
    ばん
    0.08
    लेज
    0.08
    VAS
    0.08
    Activations Density 0.000%

    No Known Activations