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. 56285
    Prev
    Next
    INDEX
    Explanations

    Best

    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
    轴
    -0.07
    rd
    -0.07
     powering
    -0.07
    atten
    -0.07
    .mine
    -0.07
     Limb
    -0.07
    Ni
    -0.07
     Cord
    -0.07
     targ
    -0.07
    xd
    -0.07
    POSITIVE LOGITS
     julọ
    0.09
    -selling
    0.09
     kakhulu
    0.09
     suited
    0.08
    तम
    0.08
     الإم
    0.08
    сел
    0.08
     behaved
    0.08
     oyster
    0.08
    ত্ব
    0.08
    Activations Density 0.062%

    No Known Activations