© 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. 548
    Prev
    Next
    INDEX
    Explanations

    bot

    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
    ATAR
    -0.08
     AVR
    -0.08
    -0.08
    ANCEL
    -0.08
    pheres
    -0.08
    UBLE
    -0.08
     Resin
    -0.07
     HDD
    -0.07
     granny
    -0.07
    SOLE
    -0.07
    POSITIVE LOGITS
     Stark
    0.09
    Permissions
    0.09
     权
    0.08
     Lambert
    0.08
     endorsement
    0.08
     anonymously
    0.08
    .permissions
    0.08
    ermission
    0.08
    ermissions
    0.08
     Permissions
    0.08
    Activations Density 0.002%
    No Known Activations