© 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. 47818
    Prev
    Next
    INDEX
    Explanations

    say

    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
     Zar
    -0.08
     Pedro
    -0.07
     EEPROM
    -0.07
     Peter
    -0.07
     Joseph
    -0.07
     Ud
    -0.07
     Otto
    -0.07
    -0.07
    的钱
    -0.07
    Central
    -0.07
    POSITIVE LOGITS
     attribut
    0.09
    _feats
    0.09
     clich
    0.08
     descriptors
    0.08
     couch
    0.08
     enforce
    0.08
     бә
    0.08
     duvet
    0.08
    描
    0.08
     rhetoric
    0.08
    Activations Density 0.007%
    No Known Activations