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. 58818
    Prev
    Next
    INDEX
    Explanations

    Autograph signings

    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
     μην
    -0.08
    _velocity
    -0.08
    Virt
    -0.08
     hydraul
    -0.08
    Male
    -0.08
    Semester
    -0.08
    Built
    -0.08
    _minor
    -0.07
     Powerful
    -0.07
    _timer
    -0.07
    POSITIVE LOGITS
     memorabilia
    0.11
     autograph
    0.10
     cosplay
    0.10
     fãs
    0.10
     honoring
    0.10
     meetup
    0.10
     celebrities
    0.09
     handshake
    0.09
     Meetup
    0.09
     Comic
    0.09
    Activations Density 0.052%

    No Known Activations