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. 130375
    Prev
    Next
    INDEX
    Explanations

    loft

    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
     MACH
    -0.08
     nač
    -0.07
     Mach
    -0.07
     görü
    -0.07
     kurz
    -0.07
     pearl
    -0.07
     motorists
    -0.07
     sodium
    -0.07
     �
    -0.07
     kurang
    -0.07
    POSITIVE LOGITS
     chic
    0.09
     الهواء
    0.09
     spacious
    0.08
     apartment
    0.08
     sleeve
    0.08
     ಯುವ
    0.08
     loft
    0.07
     amend
    0.07
     яшь
    0.07
     Beginner
    0.07
    Activations Density 0.002%

    No Known Activations