Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 2187
    Prev
    Next
    INDEX
    Explanations

    4 or 0

    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
    -0.09
     Donation
    -0.08
    Covid
    -0.08
     Uy
    -0.08
    .patch
    -0.08
    Kan
    -0.07
     Kan
    -0.07
     Rental
    -0.07
     Rent
    -0.07
     oblig
    -0.07
    POSITIVE LOGITS
     sonora
    0.07
     son
    0.07
     provo
    0.07
     klingt
    0.07
    697
    0.07
     günstig
    0.07
     GRO
    0.07
     الغ
    0.07
     sonic
    0.07
     попасть
    0.07
    Activations Density 0.000%

    No Known Activations