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. 76289
    Prev
    Next
    INDEX
    Explanations

    for

    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
     elective
    -0.08
     exemplar
    -0.08
    tene
    -0.08
     condenser
    -0.08
    uggestion
    -0.07
     (=
    -0.07
     폭
    -0.07
    LIBINT
    -0.07
    ahre
    -0.07
    landır
    -0.07
    POSITIVE LOGITS
     إقامة
    0.08
     склада
    0.08
     sunny
    0.08
     любят
    0.08
     പേർ
    0.08
     organiseert
    0.08
     stellen
    0.08
     VIC
    0.08
    Busy
    0.08
     sple
    0.08
    Activations Density 0.005%

    No Known Activations