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. 11-RESID-POST-AA
    6. 56216
    Prev
    Next
    INDEX
    Explanations

    Adverbs and size/temperature adjectives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     metabolism
    -0.08
    olong
    -0.07
     obnov
    -0.07
     UND
    -0.07
     synthes
    -0.07
     predstav
    -0.07
    elly
    -0.07
    -digit
    -0.07
    xt
    -0.07
     realizou
    -0.06
    POSITIVE LOGITS
     जित
    0.09
    _than
    0.09
     than
    0.08
    0.08
    Than
    0.08
    -than
    0.08
     summa
    0.08
    کاری
    0.08
     نہیں
    0.08
     footing
    0.08
    Activations Density 0.070%

    No Known Activations