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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 19445
    Prev
    Next
    INDEX
    Explanations

    family members

    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
    -valid
    -0.08
     criatura
    -0.08
     mídia
    -0.08
     afer
    -0.07
    -element
    -0.07
    _VALID
    -0.07
    Insertion
    -0.07
    fänger
    -0.07
     validity
    -0.07
     inserting
    -0.07
    POSITIVE LOGITS
     daughters
    0.12
     dads
    0.11
     wives
    0.11
     brothers
    0.11
     boys
    0.10
     solidarity
    0.10
     fathers
    0.09
     dudes
    0.09
     hombres
    0.09
     sons
    0.09
    Activations Density 0.117%

    No Known Activations