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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 49335
    Prev
    Next
    INDEX
    Explanations

    atus

    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
     Transformer
    -0.08
    ((((
    -0.08
    .mixin
    -0.08
    /Text
    -0.08
     قصة
    -0.08
    .telegram
    -0.08
     gak
    -0.08
     questionable
    -0.08
     [[[
    -0.07
     GEL
    -0.07
    POSITIVE LOGITS
     pà
    0.08
    drag
    0.07
    wright
    0.07
    stände
    0.07
    页
    0.07
     stylish
    0.07
    铜
    0.07
     indicates
    0.07
     drums
    0.07
     denotes
    0.07
    Activations Density 0.001%

    No Known Activations