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. 78655
    Prev
    Next
    INDEX
    Explanations

    b

    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
    gbọ
    -0.08
     age
    -0.07
    gera
    -0.07
    enges
    -0.07
    "text
    -0.07
     �
    -0.07
     столько
    -0.07
    -market
    -0.07
     Royce
    -0.07
     �
    -0.07
    POSITIVE LOGITS
    юй
    0.09
     anis
    0.08
    Directional
    0.08
     auteurs
    0.08
    ontal
    0.08
    轴
    0.07
     directional
    0.07
    型
    0.07
     unequal
    0.07
     फूल
    0.07
    Activations Density 0.012%

    No Known Activations