© 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. 26366
    Prev
    Next
    INDEX
    Explanations

    =

    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
     В
    -0.07
    ,提高
    -0.07
    bonne
    -0.07
    .tpl
    -0.07
     תש
    -0.07
    规律
    -0.07
    ája
    -0.07
     ול
    -0.07
    íon
    -0.07
    Ї
    -0.07
    POSITIVE LOGITS
     resist
    0.08
     hanga
    0.08
     enum
    0.08
    eam
    0.08
    ictim
    0.08
    (enum
    0.08
     nền
    0.08
    	enum
    0.08
    next
    0.08
    erie
    0.08
    Activations Density 0.005%

    No Known Activations