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. 30787
    Prev
    Next
    INDEX
    Explanations

    or

    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
    갑
    -0.09
    Changer
    -0.08
    疑
    -0.08
    하다
    -0.08
    했고
    -0.08
    榜
    -0.07
    hate
    -0.07
     kov
    -0.07
    ('').
    -0.07
     طن
    -0.07
    POSITIVE LOGITS
    ША
    0.08
    ��
    0.08
    shir
    0.07
     Pap
    0.07
    /context
    0.07
    ust
    0.07
    _MOVE
    0.07
     DAG
    0.07
    dist
    0.07
    Move
    0.07
    Activations Density 0.026%

    No Known Activations