© 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
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 49281
    Prev
    Next
    INDEX
    Explanations

    wave properties

    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
    .lex
    -0.08
     tax
    -0.08
    _tax
    -0.08
     Charles
    -0.08
    .tax
    -0.08
     Logout
    -0.08
     Klub
    -0.08
    OKEN
    -0.08
     taxe
    -0.08
    іл
    -0.08
    POSITIVE LOGITS
     amplitude
    0.28
     waveform
    0.26
     sinus
    0.25
    Amplitude
    0.25
     wave
    0.25
     oscill
    0.24
    _wave
    0.23
     waves
    0.23
    Wave
    0.23
     sine
    0.23
    Activations Density 0.094%

    No Known Activations