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. 53185
    Prev
    Next
    INDEX
    Explanations

    layout

    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
     کی
    -0.08
     одна
    -0.08
     deliber
    -0.08
     exploitation
    -0.08
     visitation
    -0.08
     Vi
    -0.07
     Rock
    -0.07
    Reality
    -0.07
     строки
    -0.07
     aperçu
    -0.07
    POSITIVE LOGITS
    .href
    0.09
    memberof
    0.08
    bounds
    0.08
     هیواد
    0.08
     Lund
    0.08
     egiten
    0.07
    width
    0.07
    leist
    0.07
     modifier
    0.07
    gin
    0.07
    Activations Density 0.001%

    No Known Activations