© 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. 23-RESID-POST-AA
    11. 97215
    Prev
    Next
    INDEX
    Explanations

    say 'outing' or 'outed'

    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
     хват
    -0.09
    šť
    -0.08
     distracted
    -0.08
    fuscated
    -0.08
    füg
    -0.08
    inanders
    -0.08
     degrad
    -0.08
     destruct
    -0.08
    dzi
    -0.08
    ർത്ത
    -0.08
    POSITIVE LOGITS
    outing
    0.17
    outed
    0.13
    out
    0.12
    OUT
    0.09
     éve
    0.09
    ightly
    0.09
    াউ
    0.08
    Birth
    0.08
    出生
    0.08
    ਾਉ
    0.08
    Activations Density 0.001%

    No Known Activations