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. 3-RESID-POST-AA
    6. 12486
    Prev
    Next
    INDEX
    Explanations

    möchte

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    市
    -0.09
     gn
    -0.08
     sting
    -0.08
     oda
    -0.07
    娇
    -0.07
     mistr
    -0.07
     Rig
    -0.07
    Rig
    -0.07
     cam
    -0.07
     colle
    -0.07
    POSITIVE LOGITS
     Dick
    0.09
    cfg
    0.07
    ogan
    0.07
     ಸಾರ
    0.07
     broaden
    0.07
     vyp
    0.07
     Modi
    0.07
    0.07
     താര
    0.07
     vuestro
    0.07
    Activations Density 0.001%

    No Known Activations