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. 60511
    Prev
    Next
    INDEX
    Explanations

    Dialogue in scripts/stories

    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
    ston
    -0.08
    _lbl
    -0.08
     género
    -0.08
    -Me
    -0.07
    жив
    -0.07
     generar
    -0.07
    rch
    -0.07
    _PROM
    -0.07
     ген
    -0.07
    pier
    -0.07
    POSITIVE LOGITS
     ausgestattet
    0.11
    พร
    0.09
     suitcase
    0.08
     खु
    0.08
     freshly
    0.08
     ביד
    0.08
     versehen
    0.08
     सहित
    0.07
     perched
    0.07
    인
    0.07
    Activations Density 0.047%

    No Known Activations