© 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. 49994
    Prev
    Next
    INDEX
    Explanations

    beginning of "sp" words

    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
     миллиард
    -0.09
    ેમ્બર
    -0.09
    ಂಬರ್
    -0.08
    MPI
    -0.08
     sprinkler
    -0.08
     diagonal
    -0.08
    गर
    -0.08
    amba
    -0.08
    арц
    -0.08
    celand
    -0.07
    POSITIVE LOGITS
    iritual
    0.21
     espirit
    0.15
    irit
    0.14
     espiritual
    0.13
    IRIT
    0.13
     Spiritual
    0.13
    irtual
    0.13
     spiritual
    0.13
     spiritually
    0.13
     spirituality
    0.12
    Activations Density 0.002%

    No Known Activations