© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 2643
    Prev
    Next
    INDEX
    Explanations

    blank

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     бек
    -0.08
    pbs
    -0.08
     sili
    -0.08
    crm
    -0.07
     മാത
    -0.07
     ベ
    -0.07
     commerciales
    -0.07
     doable
    -0.07
     TEC
    -0.07
     SSP
    -0.07
    POSITIVE LOGITS
    闻
    0.08
    幅
    0.08
    Tint
    0.08
     Hydro
    0.08
    中王
    0.08
    代引
    0.08
    ूत
    0.08
     tint
    0.08
    部
    0.08
    unya
    0.07
    Activations Density 0.000%

    No Known Activations