© 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 EvalsExportsAPI 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. 49384
    Prev
    Next
    INDEX
    Explanations

    Unstructured text

    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
    nit
    -0.09
    mat
    -0.08
    agr
    -0.08
     Jordan
    -0.08
    -One
    -0.08
    িভ
    -0.08
    ases
    -0.07
    -one
    -0.07
    mt
    -0.07
    othesis
    -0.07
    POSITIVE LOGITS
    .z
    0.08
     gods
    0.08
     ró
    0.07
    _ACCEL
    0.07
     словами
    0.07
    zina
    0.07
     z
    0.07
     obscene
    0.07
     portas
    0.07
     Rack
    0.07
    Activations Density 0.039%

    No Known Activations