© 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. 12744
    Prev
    Next
    INDEX
    Explanations

    Gaming

    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
    .endswith
    -0.08
     formerly
    -0.08
    .starts
    -0.07
    _Click
    -0.07
    province
    -0.07
    .ends
    -0.07
    esters
    -0.07
    .dev
    -0.07
    .digest
    -0.07
    .parse
    -0.07
    POSITIVE LOGITS
    ompok
    0.09
     sred
    0.09
     Kuw
    0.08
     Kod
    0.08
     Ks
    0.08
    STRUCTIONS
    0.08
     गठन
    0.08
    struct
    0.08
     fij
    0.08
     izy
    0.07
    Activations Density 0.000%

    No Known Activations