© 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. 23-RESID-POST-AA
    11. 96850
    Prev
    Next
    INDEX
    Explanations

    logical implication

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     характериз
    -0.08
     മത്സര
    -0.08
    -0.08
     Seren
    -0.08
     போட்ட
    -0.08
    زين
    -0.08
    ілген
    -0.07
    登记
    -0.07
    ξαν
    -0.07
    竞争
    -0.07
    POSITIVE LOGITS
     implication
    0.40
     implications
    0.37
    Imp
    0.34
    imp
    0.29
     Imp
    0.29
    _imp
    0.28
     implica
    0.26
     implic
    0.24
    .imp
    0.23
    ’imp
    0.22
    Activations Density 0.096%
    No Known Activations