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. 77309
    Prev
    Next
    INDEX
    Explanations

    The Backrooms

    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
    -rom
    -0.09
    Election
    -0.09
     sebesar
    -0.08
     honorary
    -0.08
     election
    -0.08
    _DECL
    -0.08
     horoscope
    -0.08
     ceremonial
    -0.08
     bilingual
    -0.08
    认可
    -0.08
    POSITIVE LOGITS
     eerie
    0.10
     intermin
    0.10
     horrors
    0.10
     glitches
    0.09
     intermitt
    0.09
     traps
    0.09
    迷
    0.09
     weird
    0.09
    doors
    0.09
     endlessly
    0.09
    Activations Density 0.003%

    No Known Activations