© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 18219
    Prev
    Next
    INDEX
    Explanations

    性

    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
    ness
    -0.12
    s
    -0.09
    ைந்து
    -0.09
    ින්
    -0.09
    snapshot
    -0.09
    timeline
    -0.09
    ేందుకు
    -0.08
     upwards
    -0.08
    ుతూ
    -0.08
    snd
    -0.08
    POSITIVE LOGITS
    능
    0.12
    别
    0.10
    別
    0.10
     dục
    0.10
    ственная
    0.10
    czne
    0.09
    czny
    0.09
    ование
    0.09
    কর
    0.09
    лемент
    0.09
    Activations Density 0.002%

    No Known Activations