© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 69877
    Prev
    Next
    INDEX
    Explanations

    Roman numerals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -get
    -0.08
    -and
    -0.08
     Omega
    -0.08
    etable
    -0.08
    bedingungen
    -0.08
     tabletop
    -0.07
    _table
    -0.07
     allowances
    -0.07
    ancier
    -0.07
    ാപ
    -0.07
    POSITIVE LOGITS
    .FL
    0.08
     defect
    0.07
    Phone
    0.07
    Hey
    0.07
    Ev
    0.07
    (ev
    0.07
    Pron
    0.07
     rit
    0.07
    (problem
    0.07
     hey
    0.07
    Activations Density 0.003%

    No Known Activations