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. 76291
    Prev
    Next
    INDEX
    Explanations

    of

    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
     helic
    -0.08
    DEP
    -0.08
    depart
    -0.07
     supremacy
    -0.07
    <!
    -0.07
    -China
    -0.07
    -degree
    -0.07
    adc
    -0.07
     ingr
    -0.07
    056
    -0.07
    POSITIVE LOGITS
     scraps
    0.08
     HY
    0.08
     dass
    0.08
     Hip
    0.08
     eines
    0.07
     собственного
    0.07
     sido
    0.07
     років
    0.07
     Fortress
    0.07
    _ops
    0.07
    Activations Density 0.021%

    No Known Activations