© 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. 50329
    Prev
    Next
    INDEX
    Explanations

    opt-out

    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
     borrowed
    -0.08
     quake
    -0.08
     পাহ
    -0.08
    Animating
    -0.08
     jewels
    -0.08
     planos
    -0.08
    .Lerp
    -0.08
    残局
    -0.08
    .firebaseio
    -0.07
     болж
    -0.07
    POSITIVE LOGITS
     opt
    0.23
     Opt
    0.22
    Opt
    0.21
     opting
    0.21
    opt
    0.20
     opted
    0.19
    	opt
    0.19
    .opt
    0.19
    _opt
    0.19
     unsubscribe
    0.19
    Activations Density 0.021%

    No Known Activations