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. 366
    Prev
    Next
    INDEX
    Explanations

    Language/character analysis snippets

    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
     direcion
    -0.08
    علقة
    -0.08
    afb
    -0.08
    plies
    -0.08
     није
    -0.08
     الصحي
    -0.08
    دارية
    -0.08
    asmine
    -0.08
    reffen
    -0.08
    _ir
    -0.08
    POSITIVE LOGITS
     dessen
    0.09
    aham
    0.08
     Weber
    0.08
     ago
    0.08
     Arme
    0.08
     Statistics
    0.07
     statistics
    0.07
     statistiques
    0.07
     Shar
    0.07
     domic
    0.07
    Activations Density 0.001%

    No Known Activations