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. 65250
    Prev
    Next
    INDEX
    Explanations

    7

    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
     equival
    -0.07
    115
    -0.07
     inde
    -0.07
    108
    -0.07
    116
    -0.07
     completing
    -0.07
     kon
    -0.07
     post
    -0.07
     markup
    -0.07
     through
    -0.07
    POSITIVE LOGITS
    істі
    0.09
    맨
    0.09
    给主人
    0.08
    拍拍
    0.08
    테
    0.08
     öt
    0.08
    Who's
    0.08
    이에
    0.08
    알
    0.08
    /↵/
    0.08
    Activations Density 0.001%

    No Known Activations