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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 51504
    Prev
    Next
    INDEX
    Explanations

    casting

    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
    redentials
    -0.08
    ależ
    -0.08
     SSH
    -0.07
     lorem
    -0.07
     Frankfurt
    -0.07
    SSH
    -0.07
     Μέ
    -0.07
    .mnu
    -0.07
    aditional
    -0.07
    đena
    -0.07
    POSITIVE LOGITS
     casting
    0.43
     cast
    0.42
     casts
    0.41
     Casting
    0.39
     Cast
    0.39
    .cast
    0.38
    _cast
    0.38
    Casting
    0.38
    Cast
    0.37
    casting
    0.36
    Activations Density 0.069%

    No Known Activations