© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 108694
    Prev
    Next
    INDEX
    Explanations

    relate/identify

    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
     prophyl
    -0.09
     Bethesda
    -0.08
     Hull
    -0.08
     मृत
    -0.08
     koo
    -0.08
     Bloom
    -0.08
    adam
    -0.08
     obligator
    -0.08
     alphabet
    -0.08
     UML
    -0.07
    POSITIVE LOGITS
     relatable
    0.17
     herken
    0.10
     understandable
    0.10
     empathy
    0.09
     audiences
    0.09
     experiences
    0.09
     aches
    0.09
    krips
    0.08
     véc
    0.08
     resonates
    0.08
    Activations Density 0.052%

    No Known Activations