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. 117303
    Prev
    Next
    INDEX
    Explanations

    screening

    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
    ุบ
    -0.09
     agricole
    -0.08
    agam
    -0.08
     ligero
    -0.08
    .Light
    -0.08
    속
    -0.07
     בעולם
    -0.07
     Flam
    -0.07
     salle
    -0.07
     התק
    -0.07
    POSITIVE LOGITS
    洞
    0.08
     Kleid
    0.08
    ulah
    0.07
    触
    0.07
    ствует
    0.07
    .Match
    0.07
    tle
    0.07
    检查
    0.07
    alaan
    0.07
    ohana
    0.07
    Activations Density 0.001%

    No Known Activations