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. 56241
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
     움
    -0.08
    ürü
    -0.08
    融合
    -0.08
    ür
    -0.07
    CSA
    -0.07
    /lounge
    -0.07
     fio
    -0.07
     vit
    -0.07
    irit
    -0.07
     Payroll
    -0.07
    POSITIVE LOGITS
     >=
    0.09
     <=
    0.09
     exceeds
    0.08
     supplied
    0.08
     thes
    0.08
    .Minimum
    0.07
     approaching
    0.07
    .That
    0.07
     estiver
    0.07
    Simulator
    0.07
    Activations Density 0.056%

    No Known Activations