© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 75510
    Prev
    Next
    INDEX
    Explanations

    quotation marks

    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
     sacrifice
    -0.09
     sacr
    -0.08
    尸
    -0.07
     svak
    -0.07
     मृत
    -0.07
     मालिक
    -0.07
    ിണ
    -0.07
     özellikle
    -0.07
    ----------------------------------------------------------------------
    -0.07
     kand
    -0.07
    POSITIVE LOGITS
     vague
    0.18
     unspecified
    0.17
     vaguely
    0.14
     अस्प
    0.12
     unclear
    0.12
     generic
    0.11
     undefined
    0.11
     nebul
    0.10
     encompassing
    0.10
     encompass
    0.10
    Activations Density 0.081%

    No Known Activations