© 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. 11-RESID-POST-AA
    11. 232
    Prev
    Next
    INDEX
    Explanations

    basil

    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
    licar
    -0.08
    olph
    -0.08
    /mol
    -0.08
     Volkswagen
    -0.08
     Clair
    -0.08
     ದೂರ
    -0.07
     Том
    -0.07
     От
    -0.07
     compromet
    -0.07
    .Settings
    -0.07
    POSITIVE LOGITS
     butt
    0.09
     irritation
    0.09
     bpy
    0.08
     flick
    0.08
     Buttons
    0.08
     hardly
    0.08
     حرف
    0.08
     fools
    0.07
     sticks
    0.07
     shutters
    0.07
    Activations Density 0.013%

    No Known Activations