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. 45211
    Prev
    Next
    INDEX
    Explanations

    prepositions

    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
    पत्र
    -0.09
     аппарат
    -0.08
     город
    -0.08
    _COMPLETE
    -0.08
     востреб
    -0.08
    (sig
    -0.08
     Rated
    -0.08
     Consel
    -0.07
    ают
    -0.07
    теп
    -0.07
    POSITIVE LOGITS
     повед
    0.08
     আচ
    0.08
     behavior
    0.08
     gedrag
    0.08
     Vul
    0.07
     näher
    0.07
     Himself
    0.07
     pona
    0.07
     proximal
    0.07
    _behavior
    0.07
    Activations Density 0.029%

    No Known Activations