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. 15-RESID-POST-AA
    6. 19499
    Prev
    Next
    INDEX
    Explanations

    1 or 0

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     entscheiden
    -0.08
    ir
    -0.08
     limpi
    -0.08
     bri
    -0.08
     versch
    -0.07
    brahim
    -0.07
    ersey
    -0.07
     entschieden
    -0.07
    ertig
    -0.07
    ambre
    -0.07
    POSITIVE LOGITS
     guaranteed
    0.10
     altid
    0.10
     always
    0.10
     ALWAYS
    0.10
     mandatory
    0.10
     obrigatório
    0.10
     kindlasti
    0.10
     સહિત
    0.10
     mandated
    0.09
     selalu
    0.09
    Activations Density 0.018%

    No Known Activations