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. 119375
    Prev
    Next
    INDEX
    Explanations

    calendar

    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
     enamel
    -0.08
    人民共和国
    -0.08
    壮
    -0.07
     eff
    -0.07
    ища
    -0.07
     Gallagher
    -0.07
    eri
    -0.07
     bassist
    -0.07
    ительно
    -0.07
    nienie
    -0.07
    POSITIVE LOGITS
    /calendar
    0.12
    (calendar
    0.11
    .Calendar
    0.11
    (Calendar
    0.10
    /year
    0.10
    .YEAR
    0.09
    .calendar
    0.09
    .month
    0.09
     календар
    0.09
     calendar
    0.09
    Activations Density 0.005%

    No Known Activations