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. 98
    Prev
    Next
    INDEX
    Explanations

    simplifying math expressions

    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
     لإن
    -0.08
    _API
    -0.07
     supernatural
    -0.07
    _FA
    -0.07
     البط
    -0.07
    بع
    -0.07
    ூர
    -0.07
    _PRI
    -0.07
     تامین
    -0.07
     excitement
    -0.07
    POSITIVE LOGITS
     simplify
    0.12
     simplifying
    0.12
    simpl
    0.12
    Simpl
    0.11
    Rewrite
    0.11
     Simpl
    0.11
     Expr
    0.11
     rewriting
    0.11
     Rewrite
    0.10
     simpl
    0.10
    Activations Density 0.044%

    No Known Activations