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. 58729
    Prev
    Next
    INDEX
    Explanations

    on

    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
    aser
    -0.09
     (
    -0.09
     ബാല
    -0.08
    66
    -0.08
    STRAINT
    -0.07
    ued
    -0.07
    (M
    -0.07
    (N
    -0.07
    (FILE
    -0.07
     വിദ്യാഭ്യാസ
    -0.07
    POSITIVE LOGITS
     görünt
    0.09
    在那里
    0.08
     chill
    0.08
     실제
    0.08
     echtes
    0.08
    tm
    0.08
     Umb
    0.07
     ದಾಖ
    0.07
     নিব
    0.07
     misura
    0.07
    Activations Density 0.433%

    No Known Activations