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

    Neuronpedia

    Jacobian LensNEW
    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. 23-RESID-POST-AA
    11. 49998
    Prev
    Next
    INDEX
    Explanations

    .cvt

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eded
    -0.08
    ocom
    -0.08
    _ft
    -0.08
    .I
    -0.08
    neden
    -0.07
    _Mouse
    -0.07
    opro
    -0.07
    Lt
    -0.07
    iak
    -0.07
    .Game
    -0.07
    POSITIVE LOGITS
    Color
    0.09
    -plan
    0.08
    σεις
    0.08
     imag
    0.07
    mission
    0.07
    -y
    0.07
     은
    0.07
    specifier
    0.07
    lims
    0.07
     예정
    0.07
    Activations Density 0.000%

    No Known Activations