Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11803
    Prev
    Next
    INDEX
    Explanations

    details

    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
    icamente
    -0.09
    vend
    -0.08
     criando
    -0.07
     disrupting
    -0.07
     perde
    -0.07
    协
    -0.07
    forming
    -0.07
    Recover
    -0.07
     removing
    -0.07
     રચ
    -0.07
    POSITIVE LOGITS
    amh
    0.10
    🏻
    0.09
    ></
    0.09
    ><
    0.08
    itorio
    0.07
    736
    0.07
    에서는
    0.07
    ph
    0.07
    hra
    0.07
    encia
    0.07
    Activations Density 0.004%

    No Known Activations