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. 48954
    Prev
    Next
    INDEX
    Explanations

    Currency amounts

    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
     encargado
    -0.09
     خصوص
    -0.08
     اخت
    -0.08
     �
    -0.08
    ︎
    -0.07
     فرق
    -0.07
     |=
    -0.07
     �
    -0.07
    avaju
    -0.07
     Aufgrund
    -0.07
    POSITIVE LOGITS
     thresholds
    0.09
     taxable
    0.08
     exemption
    0.08
    תר
    0.08
     public
    0.08
            		
    0.07
     exempt
    0.07
     exemptions
    0.07
    ಗಳ
    0.07
    Expanded
    0.07
    Activations Density 0.010%

    No Known Activations