© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 103427
    Prev
    Next
    INDEX
    Explanations

    tangent calculations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     తగ్గ
    -0.10
     pdata
    -0.08
     कमी
    -0.08
     strategies
    -0.08
     minimal
    -0.08
     data
    -0.08
     डेटा
    -0.08
     reduced
    -0.08
     परिण
    -0.07
    $data
    -0.07
    POSITIVE LOGITS
    ಿಸಿದ್ದಾರೆ
    0.09
     Ket
    0.09
     Ratio
    0.09
     Several
    0.08
     grote
    0.08
    onzo
    0.08
     Following
    0.08
     Rol
    0.08
     Electric
    0.08
    orthern
    0.08
    Activations Density 0.001%

    No Known Activations