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. 11597
    Prev
    Next
    INDEX
    Explanations

    verbs

    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
    Ventas
    -0.08
    ankar
    -0.07
    aira
    -0.07
    ય
    -0.07
    argon
    -0.07
    sales
    -0.07
    idagi
    -0.07
    (args
    -0.07
     beim
    -0.07
    anek
    -0.07
    POSITIVE LOGITS
     timeframe
    0.13
    期间
    0.12
     époque
    0.12
     época
    0.11
    时期
    0.11
     berlangsung
    0.11
     సమయంలో
    0.11
     기간
    0.11
     era
    0.10
    期間
    0.10
    Activations Density 0.086%

    No Known Activations