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. 112261
    Prev
    Next
    INDEX
    Explanations

    Abbreviations

    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
     विवरण
    -0.09
     abl
    -0.08
     એમ
    -0.08
     aus
    -0.07
    पट
    -0.07
    [src
    -0.07
     वे
    -0.07
     গুরুত্ব
    -0.07
     liegt
    -0.07
     alle
    -0.07
    POSITIVE LOGITS
    Gregorian
    0.08
    Beer
    0.08
    Sue
    0.08
    Hindi
    0.08
    Kana
    0.08
    uron
    0.08
    uchsia
    0.08
    Hell
    0.07
    Upper
    0.07
    Greg
    0.07
    Activations Density 0.009%

    No Known Activations