© 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. 99200
    Prev
    Next
    INDEX
    Explanations

    source

    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
     keel
    -0.08
     Schloss
    -0.08
    シャ
    -0.08
     हल
    -0.07
    ימה
    -0.07
     min
    -0.07
    making
    -0.07
     уж
    -0.07
    asha
    -0.07
     declara
    -0.07
    POSITIVE LOGITS
    渠道
    0.11
    来源
    0.10
     источ
    0.10
     attribution
    0.09
     Organic
    0.09
    .sources
    0.09
    Organic
    0.09
    來源
    0.09
    organic
    0.09
    /source
    0.08
    Activations Density 0.007%

    No Known Activations