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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 48211
    Prev
    Next
    INDEX
    Explanations

    blood components

    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
     underwater
    -0.09
    نن
    -0.08
     Catch
    -0.08
    ుతోంది
    -0.08
    -catching
    -0.08
     αντικ
    -0.08
    ుతున్న
    -0.08
    rapper
    -0.07
     piston
    -0.07
     glyph
    -0.07
    POSITIVE LOGITS
     um
    0.13
     plasma
    0.12
     peripheral
    0.12
     Peripheral
    0.12
     donated
    0.12
     pooled
    0.12
     cord
    0.12
     fresh
    0.12
    -derived
    0.12
     Buffy
    0.12
    Activations Density 0.011%

    No Known Activations