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. 9143
    Prev
    Next
    INDEX
    Explanations

    (

    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
     bends
    -0.08
     floors
    -0.08
     footh
    -0.07
     scrambled
    -0.07
     CRE
    -0.07
     rikt
    -0.07
     focussed
    -0.07
    ICOS
    -0.07
    erz
    -0.07
     mexicano
    -0.07
    POSITIVE LOGITS
    简称
    0.08
    Hotel
    0.08
    August
    0.08
    以下简称
    0.07
    דות
    0.07
    dele
    0.07
    ্
    0.07
    asco
    0.07
    abat
    0.07
    block
    0.07
    Activations Density 0.030%

    No Known Activations