© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 102798
    Prev
    Next
    INDEX
    Explanations

    say "believe"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     =
    -0.10
    ="//
    -0.08
     zelo
    -0.08
    =
    -0.07
     advantage
    -0.07
    ++;↵↵
    -0.07
    gao
    -0.07
     interesados
    -0.07
     avenue
    -0.07
     the
    -0.07
    POSITIVE LOGITS
     disbelief
    0.22
    相信
    0.22
     믿
    0.22
     unbelievable
    0.22
     believing
    0.21
     believe
    0.21
     croy
    0.20
     বিশ্বাস
    0.20
     Believe
    0.20
     विश्वास
    0.20
    Activations Density 0.014%

    No Known Activations