Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 58434
    Prev
    Next
    INDEX
    Explanations

    prove

    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
     depreciation
    -0.11
    แม่
    -0.08
     depreci
    -0.08
     sinh
    -0.08
     turb
    -0.08
     steroid
    -0.08
     cosine
    -0.08
     узна
    -0.08
     taxable
    -0.08
    calculator
    -0.08
    POSITIVE LOGITS
    Lemma
    0.11
    Guarante
    0.11
     Guarante
    0.10
     অভিয
    0.10
     guarantee
    0.10
     proofs
    0.10
     Guarantee
    0.10
    Proof
    0.10
     guarantees
    0.09
     guaranteeing
    0.09
    Activations Density 0.057%

    No Known Activations