© 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. 19-RESID-POST-AA
    11. 102850
    Prev
    Next
    INDEX
    Explanations

    A or B

    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
    abby
    -0.09
    cheon
    -0.09
    mis
    -0.09
    wad
    -0.09
     жок
    -0.08
    mix
    -0.08
     guzti
    -0.08
     felly
    -0.08
    loko
    -0.08
    _mix
    -0.08
    POSITIVE LOGITS
    -results
    0.08
    -known
    0.08
    Implicit
    0.08
     patiënten
    0.08
     forvent
    0.08
    .expected
    0.07
    .INFO
    0.07
    -blog
    0.07
     diferença
    0.07
    -x
    0.07
    Activations Density 0.000%

    No Known Activations