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. 11637
    Prev
    Next
    INDEX
    Explanations

    Leaders' titles

    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
    :=
    -0.07
    ేస్త
    -0.07
    Stories
    -0.07
    enses
    -0.07
    .me
    -0.07
    username
    -0.07
    .root
    -0.07
    ’s
    -0.07
    .Me
    -0.06
     أثناء
    -0.06
    POSITIVE LOGITS
    ghị
    0.08
    antino
    0.08
     دستی
    0.08
    'ent
    0.08
     likewise
    0.08
     périph
    0.07
     ihres
    0.07
    ankan
    0.07
    jük
    0.07
    []}
    0.07
    Activations Density 0.100%

    No Known Activations