© 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. 51311
    Prev
    Next
    INDEX
    Explanations

    p

    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
    كانية
    -0.08
    می
    -0.08
    _Invoke
    -0.08
    طن
    -0.08
    _ALL
    -0.08
    كاني
    -0.08
     ons
    -0.07
     genotype
    -0.07
     Иг
    -0.07
     отображ
    -0.07
    POSITIVE LOGITS
    .white
    0.08
    十一
    0.08
     duty
    0.08
    аете
    0.07
    amodel
    0.07
    .tests
    0.07
    .decoder
    0.07
    .equal
    0.07
    .le
    0.07
    @Data
    0.07
    Activations Density 0.000%

    No Known Activations