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. 3-RESID-POST-AA
    6. 2292
    Prev
    Next
    INDEX
    Explanations

    order

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bə
    -0.09
    Semester
    -0.08
     Eesti
    -0.08
    bita
    -0.08
    Gross
    -0.08
     semester
    -0.08
    duu
    -0.08
     flap
    -0.08
    she
    -0.08
    Semana
    -0.08
    POSITIVE LOGITS
    ிட
    0.08
     অন্যতম
    0.08
     issuance
    0.08
     sind
    0.07
    ிந்த
    0.07
     najbardziej
    0.07
     সবচ
    0.07
     Cry
    0.07
    /cr
    0.07
     পাও
    0.07
    Activations Density 0.000%

    No Known Activations