© 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. 23-RESID-POST-AA
    11. 49590
    Prev
    Next
    INDEX
    Explanations

    Pé

    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
    소년
    -0.08
     장
    -0.08
     mo
    -0.07
     splash
    -0.07
     Bes
    -0.07
     vein
    -0.07
     кары
    -0.07
     saba
    -0.07
     overdue
    -0.07
    osomal
    -0.07
    POSITIVE LOGITS
    lda
    0.14
    ld
    0.11
    ριο
    0.11
    dagog
    0.10
     ld
    0.09
    రిగ
    0.09
    రూ
    0.09
    LD
    0.09
    ter
    0.09
    ريون
    0.09
    Activations Density 0.001%

    No Known Activations