© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 96838
    Prev
    Next
    INDEX
    Explanations

    �

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vitra
    -0.08
     jde
    -0.08
    /Delete
    -0.08
    しか
    -0.08
    Corre
    -0.08
     bowed
    -0.07
    retto
    -0.07
    siniz
    -0.07
     pire
    -0.07
    pard
    -0.07
    POSITIVE LOGITS
    �
    0.18
    urring
    0.09
    �ট
    0.09
    ঘ
    0.09
    ਘ
    0.08
    ಘ
    0.08
    घ
    0.08
     ઘ
    0.07
    ósitos
    0.07
     engag
    0.07
    Activations Density 0.002%

    No Known Activations