© 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. 2646
    Prev
    Next
    INDEX
    Explanations

    对

    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
    _attr
    -0.07
     Bennett
    -0.07
     Lak
    -0.07
     Vertreter
    -0.07
    sell
    -0.07
    -0.07
    Attr
    -0.07
     Oliver
    -0.07
     Richter
    -0.07
     Politik
    -0.07
    POSITIVE LOGITS
    각
    0.08
     ionic
    0.07
     πολλ
    0.07
    ия
    0.07
    _each
    0.07
    임
    0.07
     volta
    0.07
    _voltage
    0.07
     Homme
    0.07
     particulier
    0.07
    Activations Density 0.002%
    No Known Activations