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. 54180
    Prev
    Next
    INDEX
    Explanations

    anel

    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
     cocoa
    -0.09
     Hr
    -0.08
    حديد
    -0.07
     neon
    -0.07
     Entwickler
    -0.07
     apă
    -0.07
     Neon
    -0.07
     बाद
    -0.07
    ropic
    -0.07
     jun
    -0.07
    POSITIVE LOGITS
     agen
    0.10
     aga
    0.08
     gelingt
    0.08
     weave
    0.08
    azas
    0.08
     instrumento
    0.08
    ционного
    0.08
     {{$
    0.08
    ught
    0.07
     adhere
    0.07
    Activations Density 0.001%

    No Known Activations