© 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. 3-RESID-POST-AA
    11. 12980
    Prev
    Next
    INDEX
    Explanations

    condition

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     amassed
    -0.08
     Taurus
    -0.08
    alwa
    -0.07
    _MM
    -0.07
    ujos
    -0.07
    _pose
    -0.07
     authorised
    -0.07
     Stein
    -0.07
     Bloomberg
    -0.07
     assembled
    -0.07
    POSITIVE LOGITS
     constraints
    0.09
    Constraints
    0.08
     rằng
    0.08
     Constraint
    0.08
     Constraints
    0.08
     আক
    0.07
    _constraints
    0.07
     constraint
    0.07
    0.07
     sopra
    0.07
    Activations Density 0.031%
    No Known Activations