© 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
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 1416
    Prev
    Next
    INDEX
    Explanations

    measurements and dimensions

    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
    ঙ
    -0.09
    uais
    -0.08
    为空
    -0.08
    ▒
    -0.08
    ennig
    -0.08
    瓦
    -0.08
    adong
    -0.08
    אַנג
    -0.08
     ඇති
    -0.07
    ’র
    -0.07
    POSITIVE LOGITS
     progressive
    0.08
     Thunder
    0.07
     karm
    0.07
     layered
    0.07
     nour
    0.07
     JB
    0.07
     Cof
    0.07
    pron
    0.07
     Pare
    0.07
     tôt
    0.07
    Activations Density 0.000%

    No Known Activations