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. 23285
    Prev
    Next
    INDEX
    Explanations

    Combinatorics

    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
    'ng
    -0.08
    brew
    -0.08
     CBD
    -0.08
    ্ণ
    -0.08
     alkohol
    -0.08
     ●
    -0.08
    (Filter
    -0.07
     функциони
    -0.07
    ng
    -0.07
     kommunen
    -0.07
    POSITIVE LOGITS
     Converts
    0.09
     converts
    0.09
     convert
    0.08
    倍
    0.08
     factor
    0.08
     dedicar
    0.08
    邀
    0.07
     associa
    0.07
     extras
    0.07
     Classroom
    0.07
    Activations Density 0.014%

    No Known Activations