© 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. 11-RESID-POST-AA
    11. 24787
    Prev
    Next
    INDEX
    Explanations

    /auth

    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
     Prescott
    -0.08
     illness
    -0.08
    .apps
    -0.07
     Aufgabe
    -0.07
     Krankheit
    -0.07
    inzi
    -0.07
    ی
    -0.07
    يجة
    -0.07
    Aus
    -0.07
    .jobs
    -0.07
    POSITIVE LOGITS
     hf
    0.08
     lợi
    0.08
    లి
    0.08
    hf
    0.07
     Julien
    0.07
    iné
    0.07
    222
    0.07
     révolution
    0.07
    culated
    0.07
    ráð
    0.07
    Activations Density 0.000%

    No Known Activations