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. 58104
    Prev
    Next
    INDEX
    Explanations

    greater than or equal to

    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
     opr
    -0.08
    Stake
    -0.08
    νώ
    -0.07
     eigenlijk
    -0.07
     виж
    -0.07
    ěl
    -0.07
     conducts
    -0.07
    Advance
    -0.07
    ой
    -0.07
     condu
    -0.07
    POSITIVE LOGITS
     Vital
    0.09
     Aller
    0.08
    ifton
    0.08
     Barnes
    0.08
     Yu
    0.07
     apel
    0.07
     Mous
    0.07
     Yoo
    0.07
    ünder
    0.07
     Adam
    0.07
    Activations Density 0.026%

    No Known Activations