© 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. 3-RESID-POST-AA
    11. 2588
    Prev
    Next
    INDEX
    Explanations

    к

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Largo
    -0.08
     wage
    -0.08
    جم
    -0.08
     hinweg
    -0.07
     Patr
    -0.07
     Henrik
    -0.07
    ക്കാര
    -0.07
     procure
    -0.07
     Essex
    -0.07
     regulator
    -0.07
    POSITIVE LOGITS
    ूड
    0.08
     विक
    0.08
     toler
    0.08
    .Conn
    0.08
    ้า
    0.08
    neur
    0.07
    _CONF
    0.07
    ואל
    0.07
    уд
    0.07
    ът
    0.07
    Activations Density 0.003%

    No Known Activations