© 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. 2592
    Prev
    Next
    INDEX
    Explanations

    code and data

    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
    dig
    -0.09
     наб
    -0.08
     вп
    -0.07
     Granite
    -0.07
    rb
    -0.07
     Fert
    -0.07
    ивание
    -0.07
     OBS
    -0.07
     مرح
    -0.07
     Wrestling
    -0.07
    POSITIVE LOGITS
    Cher
    0.08
    �
    0.08
     alph
    0.08
     pale
    0.08
    环保
    0.08
    aille
    0.07
    泡
    0.07
    -ca
    0.07
     tad
    0.07
    Trib
    0.07
    Activations Density 0.002%

    No Known Activations