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. 112223
    Prev
    Next
    INDEX
    Explanations

    2

    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
    越
    -0.08
    登陆
    -0.08
     Clears
    -0.08
     kindergarten
    -0.08
     Kindergarten
    -0.08
     �
    -0.08
     clears
    -0.08
     Trend
    -0.08
     Platz
    -0.08
     agress
    -0.08
    POSITIVE LOGITS
     చేప
    0.08
    Alchemy
    0.08
    iseach
    0.08
     exceptions
    0.08
    exceptions
    0.07
    Turkey
    0.07
     සැ
    0.07
     subsidi
    0.07
    mouse
    0.07
    իշ
    0.07
    Activations Density 0.001%

    No Known Activations