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. 44270
    Prev
    Next
    INDEX
    Explanations

    Code and foreign languages

    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
    isti
    -0.08
     beam
    -0.08
     proced
    -0.07
    beam
    -0.07
     bao
    -0.07
     vary
    -0.07
     <>
    -0.07
     venn
    -0.07
     Brenda
    -0.07
     Winkel
    -0.07
    POSITIVE LOGITS
     Flesh
    0.08
     عزیز
    0.08
    akanaka
    0.08
    елей
    0.07
     гораздо
    0.07
    erseits
    0.07
     намного
    0.07
     вовсе
    0.07
     extrêmement
    0.07
     осв
    0.07
    Activations Density 0.000%

    No Known Activations