© 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. 30980
    Prev
    Next
    INDEX
    Explanations

    postpone topic for later

    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
     are
    -0.08
     is
    -0.08
     at
    -0.08
     were
    -0.08
     followed
    -0.07
    (ad
    -0.07
    :↵↵
    -0.07
     borde
    -0.07
     Orlando
    -0.07
    hum
    -0.07
    POSITIVE LOGITS
    Ệ
    0.09
     onderwerpen
    0.08
     ocasión
    0.08
    iteľ
    0.08
    ammen
    0.08
     tyranny
    0.08
     ocasião
    0.08
     અલગ
    0.08
     ایسی
    0.08
    Vier
    0.07
    Activations Density 0.016%

    No Known Activations