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. 3-RESID-POST-AA
    6. 12342
    Prev
    Next
    INDEX
    Explanations

    relations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cinem
    -0.08
     homo
    -0.08
     XR
    -0.08
     Bip
    -0.08
     ent
    -0.07
     bx
    -0.07
     Cass
    -0.07
     ndu
    -0.07
     Carm
    -0.07
    -0.07
    POSITIVE LOGITS
     sensational
    0.09
    igate
    0.08
    rand
    0.07
    杆
    0.07
     Nightmare
    0.07
    trend
    0.07
     Stephanie
    0.07
    iane
    0.07
     uh
    0.07
    brite
    0.07
    Activations Density 0.005%

    No Known Activations