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. 15-RESID-POST-AA
    6. 19118
    Prev
    Next
    INDEX
    Explanations

    2

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Primary
    -0.08
    _Controller
    -0.08
     the
    -0.08
    _CONTROLLER
    -0.07
    Axis
    -0.07
    xis
    -0.07
     -
    -0.07
     a
    -0.07
     =
    -0.07
    ಿಸಿದ
    -0.07
    POSITIVE LOGITS
     Etc
    0.09
     dret
    0.09
     cair
    0.09
    और
    0.09
     ....↵
    0.08
     ??↵↵
    0.08
     …↵
    0.08
    इसके
    0.08
     문의
    0.08
     caer
    0.08
    Activations Density 0.001%

    No Known Activations