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. 76005
    Prev
    Next
    INDEX
    Explanations

    config

    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
     উদ্দেশ
    -0.09
     सहायता
    -0.09
     apare
    -0.08
     impulso
    -0.08
    _rev
    -0.08
    appe
    -0.08
    ,e
    -0.07
     redu
    -0.07
    -ending
    -0.07
     BDSM
    -0.07
    POSITIVE LOGITS
    liefer
    0.09
     House
    0.08
    घर
    0.08
    House
    0.08
    Album
    0.08
    een
    0.07
    .house
    0.07
     house
    0.07
     precar
    0.07
     curated
    0.07
    Activations Density 0.001%

    No Known Activations