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. 53103
    Prev
    Next
    INDEX
    Explanations

    just

    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
    �
    -0.08
     Mull
    -0.08
    /settings
    -0.08
    BUR
    -0.08
    hões
    -0.08
     oll
    -0.08
    _grp
    -0.08
    -System
    -0.08
    .Binary
    -0.07
    empts
    -0.07
    POSITIVE LOGITS
     !
    0.08
    estanding
    0.07
     I'll
    0.07
    Login
    0.07
     gure
    0.07
     CS
    0.07
    CS
    0.07
     las
    0.07
    먹
    0.07
     not
    0.07
    Activations Density 0.063%

    No Known Activations