© 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. 7-RESID-POST-AA
    11. 1375
    Prev
    Next
    INDEX
    Explanations

    ing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     leftovers
    -0.09
     hlau
    -0.09
    歓
    -0.08
     trots
    -0.08
    เจ
    -0.08
     тух
    -0.08
     thaiv
    -0.08
     khoom
    -0.08
     piemē
    -0.08
     attained
    -0.08
    POSITIVE LOGITS
     instanceof
    0.08
    105
    0.08
    .flatten
    0.08
    ?)
    0.08
    aggregate
    0.08
    RB
    0.07
    .R
    0.07
    lookup
    0.07
    RT
    0.07
    ount
    0.07
    Activations Density 0.000%

    No Known Activations