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. 78737
    Prev
    Next
    INDEX
    Explanations

    rectangular

    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
     mish
    -0.10
     Malawi
    -0.09
     hips
    -0.08
     וכ
    -0.08
     Foam
    -0.08
     Chin
    -0.08
     భారీ
    -0.08
     przestr
    -0.08
    χι
    -0.08
     enorm
    -0.08
    POSITIVE LOGITS
    別
    0.08
     fractional
    0.07
    σμα
    0.07
    -pass
    0.07
    470
    0.07
    記事
    0.07
     expressions
    0.07
     substitutes
    0.07
    入力
    0.07
    詞
    0.07
    Activations Density 0.002%

    No Known Activations