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. 11-RESID-POST-AA
    6. 90107
    Prev
    Next
    INDEX
    Explanations

    citations

    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
    .timeline
    -0.08
     floppy
    -0.07
     tun
    -0.07
     से
    -0.07
     monta
    -0.07
     ojo
    -0.07
     الرق
    -0.07
    [M
    -0.07
    .Padding
    -0.07
    preté
    -0.07
    POSITIVE LOGITS
     согласно
    0.08
    rase
    0.08
    еша
    0.08
    radh
    0.07
     assent
    0.07
     Lour
    0.07
     בעל
    0.07
    quets
    0.07
     scm
    0.07
    rale
    0.07
    Activations Density 0.004%

    No Known Activations