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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 96401
    Prev
    Next
    INDEX
    Explanations

    Informal speech

    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
     өзінің
    -0.09
    isée
    -0.09
     nawe
    -0.09
    olph
    -0.08
     Ihnen
    -0.08
    その他
    -0.08
     עב
    -0.08
     інших
    -0.08
    �ლ
    -0.08
    izzata
    -0.08
    POSITIVE LOGITS
     можете
    0.17
    ’re
    0.17
     хотите
    0.15
     છો
    0.14
     શકો
    0.13
     yourself
    0.13
     guys
    0.13
     pouvez
    0.13
    Tube
    0.13
     are
    0.13
    Activations Density 0.788%

    No Known Activations