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. 15-RESID-POST-AA
    6. 18808
    Prev
    Next
    INDEX
    Explanations

    Heading or nodding

    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
    kert
    -0.08
     reveals
    -0.08
     plots
    -0.08
    actal
    -0.08
    lost
    -0.08
     plotted
    -0.08
    umer
    -0.08
     privacy
    -0.08
    yf
    -0.08
     Arc
    -0.07
    POSITIVE LOGITS
     volley
    0.10
    (Collider
    0.09
     haber
    0.09
     Norman
    0.09
    碰
    0.09
     Kai
    0.09
    撞
    0.08
    ädchen
    0.08
     الرد
    0.08
    回应
    0.08
    Activations Density 0.013%

    No Known Activations