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. 113006
    Prev
    Next
    INDEX
    Explanations

    Negative consequences

    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
    _ROUTE
    -0.08
     വിശദ
    -0.07
    gies
    -0.07
    ride
    -0.07
     Sister
    -0.07
     Ud
    -0.07
    Guide
    -0.07
    ^(
    -0.07
    _EX
    -0.07
     сделали
    -0.07
    POSITIVE LOGITS
     wors
    0.14
     ухуд
    0.13
     worsening
    0.13
     worse
    0.13
     repercussions
    0.12
     worsen
    0.12
     consequences
    0.12
    无法
    0.12
     exacerb
    0.12
    严重
    0.12
    Activations Density 0.116%

    No Known Activations