© 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. 50673
    Prev
    Next
    INDEX
    Explanations

    rid

    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
    FOR
    -0.09
     mutations
    -0.08
    isher
    -0.08
     mutation
    -0.07
    -0.07
    utate
    -0.07
     Saul
    -0.07
     FOR
    -0.07
    inta
    -0.07
    uiting
    -0.07
    POSITIVE LOGITS
    enangkan
    0.09
     luminous
    0.08
    GRAM
    0.08
     occupations
    0.08
    uce
    0.08
    ocup
    0.08
    _busy
    0.08
     amp
    0.08
    OWN
    0.08
    colm
    0.08
    Activations Density 0.000%
    No Known Activations