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. 78619
    Prev
    Next
    INDEX
    Explanations

    dashes

    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
     Через
    -0.08
     hasta
    -0.08
     lidí
    -0.08
    SAL
    -0.08
     Minimum
    -0.07
     sorties
    -0.07
    хоз
    -0.07
     вход
    -0.07
     Mindest
    -0.07
    -0.07
    POSITIVE LOGITS
     फूल
    0.09
    arns
    0.08
    AM
    0.07
    �
    0.07
    YN
    0.07
    hlung
    0.07
    禽
    0.07
    YYY
    0.07
    enticate
    0.07
     Karin
    0.07
    Activations Density 0.036%

    No Known Activations