© 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. 1313
    Prev
    Next
    INDEX
    Explanations

    ный

    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
     Shin
    -0.08
    nal
    -0.08
    unlikely
    -0.08
     TH
    -0.08
     transcend
    -0.08
     pung
    -0.07
     rocks
    -0.07
     Fang
    -0.07
    ermit
    -0.07
    thor
    -0.07
    POSITIVE LOGITS
     Bra
    0.07
    _PCM
    0.07
     kode
    0.07
     جهت
    0.07
    කු
    0.07
     Encycl
    0.07
     κα
    0.07
     positional
    0.07
    527
    0.07
    wert
    0.07
    Activations Density 0.003%

    No Known Activations