Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 1590
    Prev
    Next
    INDEX
    Explanations

    Negation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hels
    -0.08
    -0.07
     hel
    -0.07
    IRD
    -0.07
     eventual
    -0.07
     spectroscopy
    -0.07
    situ
    -0.07
     objective
    -0.07
     kalt
    -0.07
    etheus
    -0.07
    POSITIVE LOGITS
    ुभयो
    0.08
     teacht
    0.08
     সংবাদ
    0.08
    ुभएको
    0.08
     Souls
    0.08
     declares
    0.08
    arming
    0.08
     Unt
    0.08
     Furious
    0.08
     Jay
    0.07
    Activations Density 0.001%

    No Known Activations