Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 54114
    Prev
    Next
    INDEX
    Explanations

    picture

    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
    Workbench
    -0.08
    845
    -0.08
    炼
    -0.07
    497
    -0.07
    Inspectable
    -0.07
    ाची
    -0.07
     vial
    -0.07
    ிகளை
    -0.07
     flyer
    -0.07
     printable
    -0.07
    POSITIVE LOGITS
     segn
    0.09
     выборе
    0.09
     socioeconomic
    0.09
    .kafka
    0.08
     socio
    0.08
    amam
    0.08
    લું
    0.08
    ਲਾ
    0.08
     МО
    0.07
     sinais
    0.07
    Activations Density 0.001%

    No Known Activations