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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 78760
    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
     οποίο
    -0.08
     publier
    -0.07
     publicar
    -0.07
    .help
    -0.07
     singleton
    -0.07
     והוא
    -0.07
     geliyor
    -0.07
    פיק
    -0.07
    =\'
    -0.07
     który
    -0.07
    POSITIVE LOGITS
     Hiring
    0.10
     workforce
    0.10
     probation
    0.09
     hiring
    0.09
     уволь
    0.09
    応募
    0.09
    hire
    0.09
     auditions
    0.08
     withheld
    0.08
     Linkedin
    0.08
    Activations Density 0.022%

    No Known Activations