© 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. 23-RESID-POST-AA
    11. 5874
    Prev
    Next
    INDEX
    Explanations

    dict

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    段
    -0.08
    igkeiten
    -0.08
     днев
    -0.08
    heiten
    -0.08
     Democrats
    -0.08
     системы
    -0.08
    geteilt
    -0.08
     Dickens
    -0.07
     divis
    -0.07
     Daily
    -0.07
    POSITIVE LOGITS
    <string
    0.13
     comprehension
    0.13
    cionario
    0.13
    <TKey
    0.12
    .lookup
    0.11
    _entries
    0.11
    .entries
    0.11
    Entries
    0.11
     lookup
    0.11
    .Entry
    0.10
    Activations Density 0.009%

    No Known Activations