© 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. 30225
    Prev
    Next
    INDEX
    Explanations

    API usage

    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
     rangement
    -0.09
     Tournament
    -0.09
    Species
    -0.09
     adjective
    -0.08
     Estate
    -0.08
     Antique
    -0.08
     Kindergarten
    -0.08
     ruling
    -0.08
     wiederum
    -0.08
     Scores
    -0.08
    POSITIVE LOGITS
    _HTTP
    0.17
     axios
    0.17
     CURLOPT
    0.16
     XMLHttp
    0.16
    .HTTP
    0.15
    Axios
    0.15
    .http
    0.15
    axios
    0.15
     Axios
    0.15
     CURL
    0.15
    Activations Density 0.034%

    No Known Activations