© 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 EvalsExportsinterp-engineNEWAPI 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. 51309
    Prev
    Next
    INDEX
    Explanations

    framed

    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
    -frame
    -0.09
    inted
    -0.09
    ەم
    -0.08
    amię
    -0.08
    printed
    -0.08
    FRAME
    -0.08
    .Paths
    -0.08
    lm
    -0.08
    animated
    -0.08
     runnable
    -0.08
    POSITIVE LOGITS
     photography
    0.11
     art
    0.10
     fotografías
    0.10
     works
    0.09
    摄影
    0.09
     Fotograf
    0.09
     fotograf
    0.09
     noirs
    0.09
    写真
    0.09
     photographs
    0.09
    Activations Density 0.005%

    No Known Activations